Discriminative Sparse Image Models for Class-Specific Edge Detection and Image Interpretation

Authors:
Julien Mairal;Marius Leordeanu;Francis Bach;Martial Hebert;Jean Ponce
Affiliations:
INRIA, Paris-Rocquencourt, and WILLOW project-team, ENS/INRIA/CNRS UMR 8548, ;Carnegie Mellon University, Pittsburgh, ;INRIA, Paris-Rocquencourt, and WILLOW project-team, ENS/INRIA/CNRS UMR 8548, ;Carnegie Mellon University, Pittsburgh, ;Ecole Normale Supérieure, Paris, and WILLOW project-team, ENS/INRIA/CNRS UMR 8548,
Venue:
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
Year:
2008

Citing 0
Cited 14

Image inpainting by patch propagation using patch sparsity

IEEE Transactions on Image Processing
Facial expression recognition on multiple manifolds

Pattern Recognition
Dictionary learning based object detection and counting in traffic scenes

Proceedings of the Fourth ACM/IEEE International Conference on Distributed Smart Cameras
Boundary detection using f-measure-, filter- and feature- (F3) boost

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Categorization of multiple objects in a scene without semantic segmentation

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part I
Sulci detection in photos of the human cortex based on learned discriminative dictionaries

SSVM'11 Proceedings of the Third international conference on Scale Space and Variational Methods in Computer Vision
A particle filter framework for contour detection

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Shape sharing for object segmentation

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Efficient closed-form solution to generalized boundary detection

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
A generic model to compose vision modules for holistic scene understanding

ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part I
Discriminative dictionary learning with pairwise constraints

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Region segmentation and object extraction based on virtual edge and global features

ACCV'12 Proceedings of the 11th international conference on Computer Vision - Volume Part I
SLEDGE: Sequential Labeling of Image Edges for Boundary Detection

International Journal of Computer Vision
Learning group-based dictionaries for discriminative image representation

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Sparse signal models learned from data are widely used in audio, image, and video restoration. They have recently been generalized to discriminative image understanding tasks such as texture segmentation and feature selection. This paper extends this line of research by proposing a multiscale method to minimize least-squares reconstruction errors and discriminative cost functions under 驴0 or 驴1 regularization constraints. It is applied to edge detection, category-based edge selection and image classification tasks. Experiments on the Berkeley edge detection benchmark and the PASCAL VOC'05 and VOC'07 datasets demonstrate the computational efficiency of our algorithm and its ability to learn local image descriptions that effectively support demanding computer vision tasks.